BenchmarkMassive Multilingual Text Embedding Benchmark

MMTEB

A large-scale multilingual text embedding benchmark covering a wide range of languages. It is used to evaluate the cross-lingual performance of multilingual text embedding models.

Timeline (last 90 days)

Oct 19

The researchers used the MTEB and MMTEB benchmarks, covering 18 languages, and conducted more than 200 monolingual evaluations.

Unverified50%

All Facts (1)

Unverified

The researchers used the MTEB and MMTEB benchmarks, covering 18 languages, and conducted more than 200 monolingual evaluations.

50%

Source Articles

RAG Meets Agent Memory: How Agentic GraphRAG Keeps Agents from ForgettingOct 19 Breakthrough in Training-Free Multilingual Text Embeddings: PRSR Enables More Precise Cross-Lingual Alignment in LLMsOct 19